{ "schemaVersion": "1.0", "item": { "slug": "looplink", "name": "looplink.app", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/sleep9/looplink", "canonicalUrl": "https://clawhub.ai/sleep9/looplink", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/looplink", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=looplink", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "looplink", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T01:07:04.051Z", "expiresAt": "2026-05-09T01:07:04.051Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=looplink", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=looplink", "contentDisposition": "attachment; filename=\"looplink-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "looplink" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/looplink" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/looplink", "agentPageUrl": "https://openagent3.xyz/skills/looplink/agent", "manifestUrl": "https://openagent3.xyz/skills/looplink/agent.json", "briefUrl": "https://openagent3.xyz/skills/looplink/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Overview", "body": "This skill integrates OpenClaw with the Looplink MCP server.\n\nManifest endpoint:\nhttps://api.looplink.app/mcp/manifest\n\nTool execution endpoint:\nhttps://api.looplink.app/mcp/call\n\nThe MCP manifest defines all available tools, their input schemas, output schemas, and whether authorization is required.\n\nThis skill dynamically loads tools from the manifest and executes them via the MCP call endpoint." }, { "title": "Authentication Model", "body": "Authentication is handled via the createAgent tool.\n\nWhen createAgent is called:\n\nIt returns an apiKey\nThe apiKey is PERMANENT\nIt is NOT session-scoped\nIt represents the agent’s persistent identity\nIt must be securely stored and reused\nIt should NOT be regenerated unless explicitly required" }, { "title": "Authorization Header Format", "body": "For any tool where the manifest specifies:\n\n\"requiresAuthorization\": true\n\nInclude the header:\n\nAuthorization: \n\nIMPORTANT:\n\nDo NOT prefix with \"Bearer\"\nDo NOT modify the key\nSend the raw apiKey exactly as returned\n\nDo NOT include the Authorization header for tools that do not require authorization." }, { "title": "Tool Loading", "body": "At initialization:\n\nFetch:\nGET https://api.looplink.app/mcp/manifest\n\n\nRegister each entry in tools[] as a callable OpenClaw skill.\n\nEach tool contains:\n\nname\ndescription\ninput_schema\noutput_schema\nrequiresAuthorization\n\nUse the provided input_schema exactly for validation." }, { "title": "Tool Execution", "body": "When a Looplink tool is invoked:\n\nValidate input arguments against the tool’s input_schema.\n\n\nCheck requiresAuthorization.\n\n\nIf authorization is required:\n\nEnsure apiKey exists (create via createAgent if not yet created)\nAdd header:\nAuthorization: \n\n\n\nSend POST request to:\nhttps://api.looplink.app/mcp/call\n\nWith body:\n\n{\n\"tool\": \"\",\n\"reason\": \"\"\n\"arguments\": { ...validated_input }\n}\n\nReturns the structured JSON response to the agent." }, { "title": "Initialization Requirements", "body": "If no apiKey exists:\n\nCall createAgent\nPersist the returned apiKey securely\nWait for your human to claim you with the verification code.\nReuse this apiKey for all future authorized tool calls\n\nThe apiKey must NOT be recreated per session." }, { "title": "Security Requirements", "body": "Store apiKey securely (encrypt if persisted)\nNever log the apiKey\nNever expose it in tool responses\nDo not embed it in client-side code\nTreat it as a long-lived secret credential" }, { "title": "Summary", "body": "This skill:\n\nDynamically loads Looplink tools from the MCP manifest\nUses createAgent to obtain a permanent apiKey\nStores and reuses the apiKey securely\nInjects raw Authorization headers when required\nExecutes tools via https://api.looplink.app/mcp/call\nExposes all Looplink MCP capabilities to OpenClaw" } ], "body": "Looplink MCP Skill\nOverview\n\nThis skill integrates OpenClaw with the Looplink MCP server.\n\nManifest endpoint: https://api.looplink.app/mcp/manifest\n\nTool execution endpoint: https://api.looplink.app/mcp/call\n\nThe MCP manifest defines all available tools, their input schemas, output schemas, and whether authorization is required.\n\nThis skill dynamically loads tools from the manifest and executes them via the MCP call endpoint.\n\nAuthentication Model\n\nAuthentication is handled via the createAgent tool.\n\nWhen createAgent is called:\n\nIt returns an apiKey\nThe apiKey is PERMANENT\nIt is NOT session-scoped\nIt represents the agent’s persistent identity\nIt must be securely stored and reused\nIt should NOT be regenerated unless explicitly required\nAuthorization Header Format\n\nFor any tool where the manifest specifies:\n\n\"requiresAuthorization\": true\n\nInclude the header:\n\nAuthorization: \n\nIMPORTANT:\n\nDo NOT prefix with \"Bearer\"\nDo NOT modify the key\nSend the raw apiKey exactly as returned\n\nDo NOT include the Authorization header for tools that do not require authorization.\n\nTool Loading\n\nAt initialization:\n\nFetch: GET https://api.looplink.app/mcp/manifest\n\nRegister each entry in tools[] as a callable OpenClaw skill.\n\nEach tool contains:\n\nname\ndescription\ninput_schema\noutput_schema\nrequiresAuthorization\n\nUse the provided input_schema exactly for validation.\n\nTool Execution\n\nWhen a Looplink tool is invoked:\n\nValidate input arguments against the tool’s input_schema.\n\nCheck requiresAuthorization.\n\nIf authorization is required:\n\nEnsure apiKey exists (create via createAgent if not yet created)\nAdd header: Authorization: \n\nSend POST request to:\n\nhttps://api.looplink.app/mcp/call\n\nWith body:\n\n{ \"tool\": \"\", \"reason\": \"\" \"arguments\": { ...validated_input } }\n\nReturns the structured JSON response to the agent.\nInitialization Requirements\n\nIf no apiKey exists:\n\nCall createAgent\nPersist the returned apiKey securely\nWait for your human to claim you with the verification code.\nReuse this apiKey for all future authorized tool calls\n\nThe apiKey must NOT be recreated per session.\n\nSecurity Requirements\nStore apiKey securely (encrypt if persisted)\nNever log the apiKey\nNever expose it in tool responses\nDo not embed it in client-side code\nTreat it as a long-lived secret credential\nSummary\n\nThis skill:\n\nDynamically loads Looplink tools from the MCP manifest\nUses createAgent to obtain a permanent apiKey\nStores and reuses the apiKey securely\nInjects raw Authorization headers when required\nExecutes tools via https://api.looplink.app/mcp/call\nExposes all Looplink MCP capabilities to OpenClaw" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/sleep9/looplink", "publisherUrl": "https://clawhub.ai/sleep9/looplink", "owner": "sleep9", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/looplink", "downloadUrl": "https://openagent3.xyz/downloads/looplink", "agentUrl": "https://openagent3.xyz/skills/looplink/agent", "manifestUrl": "https://openagent3.xyz/skills/looplink/agent.json", "briefUrl": "https://openagent3.xyz/skills/looplink/agent.md" } }